| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Backout experimental adaptive-spin umtx code. | davidxu | 2007-06-06 | 1 | -67/+0 |
| * | Commit 8/14 of sched_lock decomposition. | jeff | 2007-06-04 | 1 | -33/+52 |
| * | Further system call comment cleanup: | rwatson | 2007-03-05 | 1 | -1/+0 |
| * | Add a lwpid field into per-cpu structure, the lwpid represents current | davidxu | 2006-12-20 | 1 | -0/+70 |
| * | Threading cleanup.. part 2 of several. | julian | 2006-12-06 | 1 | -6/+0 |
| * | if a thread blocked on userland condition variable is | davidxu | 2006-12-04 | 1 | -5/+10 |
| * | Introduce userspace condition variable, since we have already POSIX | davidxu | 2006-12-03 | 1 | -4/+200 |
| * | Sweep kernel replacing suser(9) calls with priv(9) calls, assigning | rwatson | 2006-11-06 | 1 | -2/+3 |
| * | Make KSE a kernel option, turned on by default in all GENERIC | jb | 2006-10-26 | 1 | -0/+6 |
| * | Optimize umtx_lock_pi() a bit by moving some heavy code out of the loop, | davidxu | 2006-10-26 | 1 | -32/+27 |
| * | In order to eliminate a branch, convert opcode to unsigned integer. | davidxu | 2006-10-25 | 1 | -2/+2 |
| * | Eliminate an unnecessary `if' statement. | davidxu | 2006-10-25 | 1 | -1/+2 |
| * | o Add keyword volatile for user mutex owner field. | davidxu | 2006-10-17 | 1 | -29/+23 |
| * | Implement 32bit umtx_lock and umtx_unlock system calls, these two system | davidxu | 2006-10-06 | 1 | -0/+14 |
| * | Fix umtx command order error for freebsd 32bit. | davidxu | 2006-09-22 | 1 | -1/+1 |
| * | Add umtx support for 32bit process on AMD64 machine. | davidxu | 2006-09-22 | 1 | -82/+440 |
| * | Merge all code of do_lock_normal, do_lock_pi and do_lock_pp into | davidxu | 2006-09-05 | 1 | -120/+52 |
| * | Check if it is root user in do_unlock_pp. | davidxu | 2006-09-03 | 1 | -2/+4 |
| * | Make sure we get new m_owner value if we can not unlock it in | davidxu | 2006-09-02 | 1 | -8/+12 |
| * | Reorder some statments. Fix typo and remove stale comments. | davidxu | 2006-08-30 | 1 | -20/+16 |
| * | Update comments about interrupted mutex locking. | davidxu | 2006-08-28 | 1 | -12/+5 |
| * | This is initial version of POSIX priority mutex support, a new userland | davidxu | 2006-08-28 | 1 | -187/+1710 |
| * | Add user priority loaning code to support priority propagation for | davidxu | 2006-08-25 | 1 | -0/+5 |
| * | Move flag TDF_UMTXQ into structure umtxq, this eliminates the requirement | davidxu | 2006-05-18 | 1 | -15/+12 |
| * | Use wakeup_one to avoid thundering herd. | davidxu | 2006-05-09 | 1 | -6/+6 |
| * | Change msleep() and tsleep() to not alter the calling thread's priority | jhb | 2006-04-17 | 1 | -6/+4 |
| * | Axe unused code. | davidxu | 2006-02-04 | 1 | -96/+0 |
| * | do umtx_wake at userland thread exit address, so that others userland | davidxu | 2005-10-26 | 1 | -3/+3 |
| * | Allocate umtx_q from heap instead of stack, this avoids | davidxu | 2005-03-05 | 1 | -34/+46 |
| * | Revert my previous errno hack, that is certainly an issue, | davidxu | 2005-01-18 | 1 | -2/+1 |
| * | make umtx timeout relative so userland can select different clock type, | davidxu | 2005-01-14 | 1 | -46/+51 |
| * | Comment out debugging printf which doesn't compile on amd64. | phk | 2005-01-12 | 1 | -0/+2 |
| * | Let _umtx_op directly return error code rather than from errno because | davidxu | 2005-01-12 | 1 | -12/+23 |
| * | Break out of loop earlier if it is not timeout. | davidxu | 2005-01-08 | 1 | -1/+1 |
| * | /* -> /*- for copyright notices, minor format tweaks as necessary | imp | 2005-01-06 | 1 | -1/+1 |
| * | Return ETIMEDOUT when thread is timeouted since POSIX thread | davidxu | 2005-01-06 | 1 | -5/+7 |
| * | Make umtx_wait and umtx_wake more like linux futex does, it is | davidxu | 2004-12-30 | 1 | -41/+9 |
| * | Make _umtx_op() as more general interface, the final parameter needn't be | davidxu | 2004-12-25 | 1 | -4/+4 |
| * | 1. introduce umtx_owner to get an owner of a umtx. | davidxu | 2004-12-25 | 1 | -3/+1 |
| * | Add umtxq_lock/unlock around umtx_signal, fix debug kernel compiling, | davidxu | 2004-12-24 | 1 | -5/+9 |
| * | 1. Fix race condition between umtx lock and unlock, heavy testing | davidxu | 2004-12-24 | 1 | -133/+104 |
| * | 1. msleep returns EWOULDBLOCK not ETIMEDOUT, use EWOULDBLOCK instead. | davidxu | 2004-12-18 | 1 | -8/+6 |
| * | 1. make umtx sharable between processes, the way is two or more processes | davidxu | 2004-12-18 | 1 | -170/+544 |
| * | Forgot to inline umtxq_unlock. | davidxu | 2004-11-30 | 1 | -1/+1 |
| * | 1. use per-chain mutex instead of global mutex to reduce | davidxu | 2004-11-30 | 1 | -115/+212 |
| * | writers must hold both sched_lock and the process lock; therefore, readers | mtm | 2004-07-12 | 1 | -5/+3 |
| * | Change the thread ID (thr_id_t) used for 1:1 threading from being a | marcel | 2004-07-02 | 1 | -3/+5 |
| * | Use the proc lock to sleep on a libthr umtx. | mtm | 2004-03-27 | 1 | -2/+6 |
| * | Return EINVAL if the contested bit is not set on the umtx passed to | tjr | 2003-09-07 | 1 | -1/+2 |
| * | Initialize 'blocked' to NULL. I think this was a real problem, but I | peter | 2003-07-23 | 1 | -0/+1 |
